poudels14 / llama2_rs_oldLinks
☆23Updated 2 years ago
Alternatives and similar repositories for llama2_rs_old
Users that are interested in llama2_rs_old are comparing it to the libraries listed below
Sorting:
- ☆131Updated last year
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆38Updated 2 years ago
- This repository has code for fine-tuning LLMs with GRPO specifically for Rust Programming using cargo as feedback☆103Updated 5 months ago
- A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust☆80Updated last year
- Inference Llama 2 in one file of pure Rust 🦀☆233Updated last year
- ☆138Updated last year
- Rust Implementation of micrograd☆52Updated last year
- A sketch of a Transformer in Rust for a blog post☆32Updated 3 years ago
- implement llava using candle☆15Updated last year
- ☆156Updated 2 years ago
- Read and write tensorboard data using Rust☆21Updated last year
- "PyTorch in Rust"☆16Updated last year
- Inference of Mamba models in pure C☆191Updated last year
- ☆61Updated last year
- High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datas…☆201Updated last month
- ☆12Updated 7 months ago
- Simplex Random Feature attention, in PyTorch☆74Updated last year
- gzip Predicts Data-dependent Scaling Laws☆35Updated last year
- ☆39Updated 2 years ago
- Understanding large language models☆118Updated 2 years ago
- A high-performance constrained decoding engine based on context free grammar in Rust☆55Updated 3 months ago
- Make triton easier☆47Updated last year
- Functional local implementations of main model parallelism approaches☆96Updated 2 years ago
- ☆26Updated 2 years ago
- Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and…☆31Updated 5 months ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆114Updated last year
- A collection of optimisers for use with candle☆40Updated 3 weeks ago
- Full finetuning of large language models without large memory requirements☆94Updated last year
- Inference engine for GLiNER models, in Rust☆66Updated last month
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆111Updated this week